Domain knowledge for surveillance applications

Versatile Information Systems, Inc. (VIS) has been applying Semantic Web technologies to the problems of situation awareness and information fusion for more than five years. Situation awareness involves the real-time processing of event-based information coming from an evolving situation in an attempt to understand what is happening. In our view, situation awareness primarily comes down to identifying higher-order relations that come into being within a situation and that have particular relevance to the problem at hand as defined by the user's goals or objectives,,,. By higher-order relations we mean relations involving multiple objects; OWL ObjectProperties represent the simplest of such relations involving two objects but situation awareness is often interested in more complex relations involving several objects. We contrast these higher-order relations with those that merely define characteristics of an individual object; DataProperties fall into this category. The analytic...

Sixth International Conference of Information Fusion, 2003. Proceedings of the, 2003

In this paper we present an ontology for situation awareness. One of our goals is to support the claim that this ontology is a reasonable candidate for representing various scenarios of situation awareness. Towards this aim we provide an explanation of the meaning of this ontology, show its expressiveness and demonstrate its extensibility. We also compare the expressiveness of this ontology with alternative approaches we considered during the design of the ontology. We then show how the ontology can be adapted to handle domain-specific situations by readily extending the core language. The extensions include adding subclasses, sub-properties and additional attributes to the core ontology. We conclude with an example of how the ontology can be used to annotate specific instances of a situation.

2018

In this study, we present an automatic generic ontology for video surveillance description, to be used as a highlevel layer in video-surveillance systems. We considered the temporal dimension of the video, using appropriate features and classification methods. Our ontology introduces six main classes; one of which is a representation for generic scene types, divided into twelve subtypes according to the number of moving objects before and after the interaction. This ontology was used to fulfill an automatic textual description of video surveillance, focusing mainly on interactions between objects. Keywords— Ontology, Video surveillance, Automatic video description, Video objects interaction, Scene type.

Proceedings of the 7th European Conference on Information Warfare

Nowadays the terrorist threat took proportions that concern governments and the national security organizations, all over the world. A successful terrorist incident usually brings catastrophic results. However if a terrorist attack can be predicted and characterized, it may be possible to organize a proper intervention in order to avoid it or to reduce its impact. The management of information is becoming an important issue in the domain of security information systems. The information access and association, analysis and assessment, and finally exploitation have become the focus for all security information services and governments. Current surveillance approaches are not very efficient leading innocent citizen to the confrontation of law enforcement services. One reason for this, result from the difficulties of the current system to extract knowledge or concepts abstracted from massive databases of information. Knowledge based methods, such as ontologies can integrate data surveillance, and enable a proper data analyse improving the performance of the security information services. This paper intends to present a perspective about the use of ontologies in the context of data surveillance, and present its importance in the current security services domain.

2004

The grand vision of the Semantic Web has led to the development of new technologies intended to serve as the groundwork for its eventual realization. Primary among these technologies is the Web ontology language OWL [1] and its more recent extension in the form of the Semantic Web rule language SWRL [2]. These languages are built upon decades of research and real-world experience in the areas of knowledge representation, automated reasoning and rule-based systems. It is fair to say that they represent (in part) the cutting edge of practical technologies for realizing intelligent agents and advanced applications. As such, these technologies are applicable to problems well beyond that represented by the Semantic Web proper. Versatile Information Systems, Inc. is committed to the development of formal yet practical reasoning systems applied to problems in the area of situation awareness and information fusion. Our recent endeavors in this area have been grounded in Semantic Web technologies and have had occasion to stress them to some of their practical limits . In our demonstration we will present the current state of our Situation Awareness Assistant (SAWA) and show how it makes use of OWL and SWRL. We will also present two supporting applications, a consistency checker for OWL documents and a graphical editor for SWRL.

7th Latin American Conference on Networked and Electronic Media (LACNEM 2017)

The availability of vast amount of closed-circuit television (CCTV) videos and the critical need for a fast and accurate analysis of all its content especially in security applications, has led to an equally urgent need for its automated processing. Indeed, identifying suspected acts of vandalism or crime from a massive collection of videos are extremely tedious using manual approach. Therefore, with application for security in mind, this paper presents a new approach for automated analysis of CCTV using ontology-based knowledge representation and reasoning. The proposed approach exploits event semantics for the identification of possible crime and perpetrators. The framework consists of salient feature extraction from CCTV footage, inter-level data parsing, highlevel conceptual model event representation, rules inferencing, knowledge reasoning and queries. Although a complete (endto-end) framework was implemented, the main contribution of this work is primarily on the high-level analysis and proposed underpinning Ontology. The proposed approach has been validated with a very large database of CCTV footage from the 2011 London riots. The results validate the strength of the approach.

The importance of visualization—discussed in the previous chapter—does not diminish the critical role that algorithmic analysis plays in achieving CSA. Algorithms reason about the voluminous observations and data about the network and infer important features of the situation that help analysts and decision-makers form their situational awareness. In order to perform this inference, and to make its output useful to other algorithms and human users, an algorithm needs to have its inputs and outputs represented in a consistent vocabulary of well-specified terms and their relations, i.e., it needs an ontology with a clear semantics and a standard. This topic is the focus of the present chapter. We already touched on the importance of semantics in the Cognition and Technology chapter. Now we discuss in detail how, in cyber operations, inference based on ontology can be used to determine the threat actor, the target and purpose in order to determine potential courses of action and future...

Lecture Notes in Computer Science, 2003

Situation Awareness involves the comprehension of the state of a collection of objects in an evolving environment. This not only includes an understanding of the objects' characteristics but also an awareness of the significant relations that hold among the objects at any point in time. Systems for establishing situation awareness require a knowledge representation for these objects and relations. Traditional ontologies, as defined with a language like DAML/OWL, are commonly used for such purposes. Unfortunately, these languages are insufficient for describing the conditions under which specific relations might hold true, which requires the explicit representation of implications, as is provided by RuleML. This paper describes an approach to knowledge representation for situation awareness employing RuleML-based domain theories constructed over OWL ontologies, presented in the context of its implementation in a Situation Awareness Assistant under development by the authors. Suggestions are also made for additions to the RuleML specification.

Situation awareness involves the identification and monitoring of relationships among objects participating in an evolving situation. This problem in general is intractable (i.e., there is a potentially infinite number of relations that could be tracked) and thus requires additional constraints and guidance defined by the user if there is to be any hope of creating practical situation awareness systems. This paper describes a Situation Awareness Assistant (SAWA) based on Semantic Web technologies that facilitates the development of user-defined domain knowledge in the form of formal ontologies and rule sets and then permits the application of the domain knowledge to the monitoring of relevant relations as they occur in evolving situations. SAWA includes tools for developing ontologies in OWL and rules in SWRL and provides runtime components for collecting event data, storing and querying the data, monitoring relevant relations and viewing the results through a graphical user interface. An application of SAWA to a scenario from the domain of supply logistics is presented along with a discussion of the challenges encountered in using SWRL for this task.

Lecture Notes in Computer Science, 2005

When developing situation awareness applications we begin by constructing an OWL ontology to capture a language of discourse for the domain of interest. Such an ontology, however, is never sufficient for fully representing the complex knowledge needed to identify what is happening in an evolving situation -this usually requires general implication afforded by a rule language such as SWRL. This paper describes the application of SWRL/OWL to the representation of knowledge intended for a supply logistics scenario. The rules are first presented in an abstract syntax based on n-ary predicates. We then describe a process to convert them into a representation that complies with the binaryonly properties of SWRL. The application of the SWRL rules is demonstrated using our situation awareness application, SAWA, which can employ either Jess or BaseVISor as its inference engine. We conclude with a summary of the issues encountered in using SWRL along with the steps taken in resolving them.